Hao Xiang

PhD Student@UCLA

About me

I am a second-year PhD student in UCLA Mobility Lab at University of California Los Angeles (UCLA). I spent wonderful two years at the beautiful San Diego area for my Master journey and got my Bachelor’s degree from Fudan University.

My research interests are computer vision, robotics and machine learning with applications on Autonomous Driving. More specifically, my research interests include:

1. Vision: cooperative perception, scene understanding, multi-modal sensor fusion, and vision-based trajectory prediction

2. Learning: adversarial learning, and multimodal learning

Education

PhD Student in Autonomous Driving
Sept. 2021 -- Now
GPA 4.0/4.0

University of California, Los Angeles
M.S. in Machine Learning and Data Science
Sept. 2019 -- Jun. 2021
GPA 4.0/4.0

University of California, San Diego
B.Eng in Microelectronics
Sept. 2015 -- Jun. 2019
GPA 3.6/4.0

Fudan University

News

1/2023: Two papers were accepted at ICRA 2023.
07/2022: One paper was accepted at ECCV 2022.
01/2022: Two papers were accepted at ICRA 2022.
12/2021: One paper was accepted at Autonomous Intelligent Systems 2021.
07/2021: One paper was accepted at ITSC 2021.
06/2020: One paper was accepted at IROS 2020.
10/2019: I joined Autonomous Vehicle Laboratory supervised by Prof. Henrik I. Christensen.
09/2019: I started my graduate study at UCSD.
06/2019: I graduated from Fudan Univsersity with outstanding undergraduate thesis award!

Selected Publications

V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer
Runsheng Xu*, Hao Xiang*, Zhengzhong Tu*, Xin Xia, Ming-Hsuan Yang Jiaqi Ma
ECCV 2022 [Paper] [Code]
The first unified transformer architecture for V2X perception, which can capture the heterogeneity of V2X systems with strong robustness against various V2X noises.

OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication
Runsheng Xu*, Hao Xiang*, Xin Xia, Xu Han Jinlong Li Jiaqi Ma
ICRA 2022 [Project] [Paper] [Code]
The first large-scale open V2V perception dataset and the first open V2V coding framework.

TridentNetV2: Lightweight Graphical Global Plan Representations for Dynamic Trajectory Generation
David Paz, Hao Xiang, Andrew Liang, Henrik I. Christensen
ICRA 2022 [Paper]
Generate dynamic trajectories for autonomous navigation via nominal graph-based global plan and a lightweight representation without the dependence on HD maps

Probabilistic Semantic Mapping for Urban Autonomous Driving Applications
David Paz*, Hengyuan Zhang*, Qinru Li*, Hao Xiang*, Henrik I. Christensen
IROS 2020 [Paper]
Build probabilistic semantic maps by leveraging segmentation network uncertainty and the LiDAR intensity prior knowledge.

Selected Projects

Particle Filter SLAM and Textured Map [Paper]
Implemented Particle Filter SLAM from scratch for stereo cameras and LiDAR data. Colored the floor of the map by using 3D geometry.

Visual-Inertial SLAM [Paper]
Implemented EKF from scratch with IMU data and camera data to jointly estimate the position of landmarks and robot.

Search-based and sampling-based algorithms for 3D-Euclidean space [Paper]
Compare performance of weighted A* and RRT/RRT* algorithms for various testing scenes. Implemented collision detection algorithms between AABB and line segment.

Heuristic-guided Reinforcement Learning Algorithms for lunar lander [Paper]
Using heuristics for all stage of training would introduce human bias. Instead of using heuristic for the final decision process, we utilize heuristic as a coach for the early stage training. Once the model has gained enough positive samples, we use a decaying factor to reduce the bias of heuristics. In this way, the algorithm can learn much faster without introducing human bias.

Contact

haxiang@g.ucla.edu